Title :
A novel method for example-based face super-resolution
Author :
Xiaofeng Wang ; Hefei Ling ; Xin Xu
Author_Institution :
Sch. of Comput. Sci. & Technol., Huazhong Univ. of Sci. & Technol., Wuhan, China
Abstract :
Face super-resolution is the specific super-resolution problem based on the property of facial images, which reconstructs a high-resolution facial image from a low-resolution input. Based on the observation that faces are made up of several relatively independent parts such as eyes, noses and mouths, we propose an example-based face hallucination framework which includes correlation-constrained non-negative matrix factorization (CCNMF) algorithm and High-dimensional Coupled NMF (HCNMF) algorithm. Compared with existing approaches, the proposed CCNMF algorithm can generate global face more similar to the ground truth face by learning a parts-based and localized representation of facial images. Moreover, residue compensation by using HCNMF can learn the relation between high-resolution residue and low-resolution residue to better preserve lost high frequency details. Experimental results verify the effectiveness of our method.
Keywords :
face recognition; image reconstruction; image representation; image resolution; matrix decomposition; CCNMF algorithm; HCNMF algorithm; correlation-constrained non-negative matrix factorization; example-based face hallucination framework; example-based face super-resolution; facial image property; facial image representation; high-dimensional coupled NMF; high-resolution facial image reconstruction; residue compensation; Image reconstruction; Image resolution; Training; face hallucination; non-negative matrix factorization; super-resolution;
Conference_Titel :
Multimedia Computing and Systems (ICMCS), 2014 International Conference on
Conference_Location :
Marrakech
Print_ISBN :
978-1-4799-3823-0
DOI :
10.1109/ICMCS.2014.6911243